Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3584 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1733. Min Act: -0.0001

Data Index: 604947 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1854. Min Act: -0.0001

Data Index: 93327 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1144414 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1355289 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1756. Min Act: -0.0001

Data Index: 175603 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1827. Min Act: -0.0001

Data Index: 69269 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1770. Min Act: -0.0001

Data Index: 1207024 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1709. Min Act: -0.0001

Data Index: 288937 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1759. Min Act: -0.0001

Data Index: 944697 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1648. Min Act: -0.0001

Data Index: 809569 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1104061 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1745. Min Act: -0.0001

Data Index: 973704 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1694. Min Act: -0.0001

Data Index: 310628 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1535. Min Act: -0.0001

Data Index: 655481 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1021840 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1214814 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1204634 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1702. Min Act: -0.0001

Data Index: 515613 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1698. Min Act: -0.0001

Data Index: 466409 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1850. Min Act: -0.0001

Data Index: 435498 (C4 (Web Text))

Max Activating Token Index: 308